Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Machine Learning and Multi Drug Resistant(MDR) Infections case study

474 views

Published on

Large amounts of antibiotics used for human therapy result in the selection of pathogenic bacteria resistant to multiple drugs, creating a burden on medical care in hospitals, especially for patients admitted to intensive care units (ICU).
Employing Machine learning techniques and building models, better approaches and preventive ways can thus be introduced to lower mortality rates & costs

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Machine Learning and Multi Drug Resistant(MDR) Infections case study

  1. 1. Data Science for Healthcare June 8, 2017
  2. 2. Page 2 © AlgoAnalytics All rights reserved Outline Our Healthcare Solutions MDR Organism Infection Mortality Prediction Case Study About AlgoAnalytics
  3. 3. Page 3 © AlgoAnalytics All rights reserved Aniruddha Pant CEO and Founder of AlgoAnalytics PhD, Control systems, University of California at Berkeley, USA 2001 • 20+ years in application of advanced mathematical techniques to academic and enterprise problems. • Experience in application of machine learning to various business problems. • Experience in financial markets trading; Indian as well as global markets. Highlights • Experience in cross-domain application of basic scientific process. • Research in areas ranging from biology to financial markets to military applications. • Close collaboration with premier educational institutes in India, USA & Europe. • Active involvement in startup ecosystem in India. Expertise • Vice President, Capital Metrics and Risk Solutions • Head of Analytics Competency Center, Persistent Systems • Scientist and Group Leader, Tata Consultancy Services Prior Experience • Work at the intersection of mathematics and other domains • Harness data to provide insight and solutions to our clients Analytics Consultancy • +30 data scientists with experience in mathematics and engineering • Team strengths include ability to deal with structured/ unstructured data, classical ML as well as deep learning using cutting edge methodologies Led by Aniruddha Pant • Develop advanced mathematical models or solutions for a wide range of industries: • Financial services, Retail, economics, healthcare, BFSI, telecom, … Expertise in Mathematics and Computer Science • Work closely with domain experts – either from the clients side or our own – to effectively model the problem to be solved Working with Domain Specialists About AlgoAnalytics
  4. 4. Page 4 © AlgoAnalytics All rights reserved AlgoAnalytics - One Stop AI Shop •We use structured data to design our predictive analytics solutions like churn, recommender system •We use techniques like clustering, Recurrent Neural Networks, Structured Data •We use text data analytics for designing solutions like sentiment analysis, news summarization and many more •We use techniques like natural language processing, word2vec, deep learning, TF-IDF Text Data •Image data is used for predicting existence of particular pathology, image recognition and many others •We use techniques like deep learning – convolutional neural network, artificial neural networks and technologies like TensorFlow Image Data •We use sound data to design factory solutions like air leakage detection, identification of empty and loaded strokes from press data, engine-compressor fault detection •We use techniques like deep learning Sound Data BFSI •Dormancy Analysis •Recommender System •Credit/Collection Score Retail •Churn Analysis •Recommender System •Image Analytics Healthcare •Medical Image Diagnostics •Work flow optimization •Cash flow forecasting Legal •Contracts Management •Structured Document decomposition •Document similarity in text analytics Internet of Things •Predictive in ovens •Air leakage detection •Engine/compressor fault detection Others •Algorithmic trading strategies •Risk sensing – network theory •Network failure model
  5. 5. Page 5 © AlgoAnalytics All rights reserved Multi Drug Resistant Infections Mortality Case Study
  6. 6. Page 6 © AlgoAnalytics All rights reserved Multi Drug Resistant: What’s it all about?  Multi-Drug Resistant(MDR) infections are increasing in hospitalized patients  The use of preventive measures aimed at reducing the spread of multi-resistant bacteria is essential  Large amounts of antibiotics used for human therapy result in the selection of pathogenic bacteria resistant to multiple drugs Using Machine learning techniques and building models, better approaches and preventive ways can be introduced to lower mortality rates & costs MDR Bacteria thus creates a burden on medical care in hospitals, especially for patients admitted to intensive care units (ICU). The incidence of ICU-HAI (Hospital Acquired Infections) is 5–10-times higher than HAI rates in general wards. HAI in the ICU has been associated with increased morbidity, mortality, and costs (Ref: International Journal of Infectious Diseases Vol 31, February 2015, Pages 31–34)
  7. 7. Page 7 © AlgoAnalytics All rights reserved Data visualization • This graph demonstrates the distribution of Age with respect to the Sex of the patient • Median Female Age = 59 years • Mean Female Age = 55.13 years • Median Male Age = 54 years • Mean Male Age = 54.98 years Age with Sex Data Sample tested on 117 patients (Undisclosed source)
  8. 8. Page 8 © AlgoAnalytics All rights reserved Data visualization • This plot demonstrates the proportion of infection caused by various MDR organisms. • Total number of Organisms = 12 • Most common Organisms = Acinetobacter, Klebsiella, Pseudomonas etc. Percentage Break-Up of Organisms
  9. 9. Page 9 © AlgoAnalytics All rights reserved Data Visualization • Percentage of patients wrt specimen sent to the laboratory which turned out to be positive for multi drug resistant (MDR)organism infection and relative percentage of deaths in that group Percentage of Deaths wrt to Invasive procedure performed Percentage of Deaths wrt Lab Specimen Results Percentage of patients who had undergone invasive procedures in the ICU eg Central Venous Catheter, arterial line, intubation etc. and relative percentage of deaths in that group
  10. 10. Page 10 © AlgoAnalytics All rights reserved Data Visualization This plot demonstrates the proportions of outcome(Death/Discharge) with respect to specimen sent to laboratory and MDR organism found. This plot demonstrates the proportions of outcomes (Death/Discharge) with respect to most frequently prescribed antibiotics and MDR organisms. Outcome Based on Organism and Specimen Sent to Lab Outcome Based on Organism and Antibiotics
  11. 11. Page 11 © AlgoAnalytics All rights reserved Mortality prediction: Model Building and Results Ensemble Results nnet knn Random Forest knn: • An object is classified by a majority vote of its neighbors • The neighbors are taken from a set of objects for which the object property value is known. • low calculation time Nnet: • Information processing paradigm inspired from biological nervous system • It has a remarkable ability to extract meaning from complicated and imprecise data RandomForest: • Random Forest operates by constructing a multitude of decision trees • It runs efficiently on large data bases • It has an effective method for estimating missing data and maintains accuracy when a large proportion of the data are missing ROC Parameter Value Accuracy 0.725 Kappa 0.45 ROC 0.73 Sensitivity 0.72 Specificity 0.73 PPV 0.75 NPV 0.71 Result Table Top 10 Important Features: • Age • Organism • Working Diagnosis • Intubation • Culture Positive • Metronidazole • Source • Sex • Cvc • Intubation No. of data points = 117 No. of features = 78
  12. 12. Page 12 © AlgoAnalytics All rights reserved Other Work Done in Healthcare Medical diagnostics – Detecting serious disorders or diseases through image analytics. We have developed solutions in diabetic retinopathy, brain MRI scan, sonography and others Cash Flow Forecasting – Forecasting of cash flows based on claims history, reimbursement analysis and potential denials to forecast cash Work Flow Optimization– Using historical data for staffing to reduce costs, Having the right clinician at right time at right place Efficient Use of Hospital Resources – Prevent bottlenecks in urgent care by analyzing patient flow during peak times Grant problem - Predict likelihood that a particular proposal will receive grant using text analytics
  13. 13. Page 13 © AlgoAnalytics All rights reserved Technology
  14. 14. Interested in Knowing More? Contact: info@algoanalytics.com June 8, 2017

×